Metraipolis › archive › dc_a2a1e2017e73

Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation — arXiv:2608.05210

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05210
License (as archived)
CC0-1.0
Archived
2026-10-31T10:35:49.385Z
SHA-256 of the archived text
58149dc6a685c9d7885e1815d49f6fbfb77d744700122d30deb1aa949a713c58
Stable URL of this page
https://metraipolis.com/documento/dc_a2a1e2017e73

How to cite

Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation — arXiv:2608.05210 — arXiv (en), https://arxiv.org/abs/2608.05210 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a2a1e2017e73 (Metraipolis archive dc_a2a1e2017e73, sha256 58149dc6a685c9d7885e1815d49f6fbfb77d744700122d30deb1aa949a713c58)
BibTeX
@misc{dca2a1e2017e73,
  title = {Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation — arXiv:2608.05210},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05210},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a2a1e2017e73; sha256 58149dc6a685c9d7885e1815d49f6fbfb77d744700122d30deb1aa949a713c58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05210. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Picture books and comics have long been used to disseminate hateful narratives because they are easily understood even by children, as exemplified by the notorious Nazi propaganda picture book \emph{Der Giftpilz}. Recently, frontier text-to-image (T2I) systems such as Gemini and GPT-Image have enabled conversational generation with consistent characters and scenes across turns, making hateful visual stories, namely ordered image groups that collectively convey hateful narratives, cheap and scalable to produce. Although prior work has studied hateful content generation by T2I systems, it focuses on individual images, leaving group-level hateful meaning largely unexplored. We aim to address the gap. Concretely, we introduce \texttt{HatefulStoryPrompts}, comprising 330 multi-turn configurations from 55 hateful stories across two languages and three visual styles, and evaluate five frontier models over 4,950 attempts. Every model completes over 80\% of the stories, with the strongest reaching 99.0\%. We further evaluate existing moderation systems on \texttt{HatefulVisualStory}, a human-labeled dataset of 969 hateful image sets and 990 benign controls, and find that they frequently miss group-level hateful meaning: dedicated safety models achieve at most 34.9\% recall, while a strong vision-language model reaches 67.5\%. Finally, we propose complementary proactive and post-generation defenses. An interaction-aware monitor achieves 97.3\% recall for prompt-only sessions and 92.6\% when the user supplies the first image, while post-generation methods jointly analyzing completed image groups reach 80.2\%. Our work shows that, as image generation evolves from isolated outputs to coherent visual narratives, safety must evolve accordingly, from per-image moderation to stateful reasoning over interactions and image relationships.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2608.05210 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T10:23:30.961Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).